Recent advancements in Artificial Intelligence (AI) have transformed the healthcare field, particularly through chatbots like ChatGPT, OpenEvidence, and MediSearch. These tools analyze complex data to aid clinical decision-making, enhancing efficiency in diagnosis, treatment planning, and patient management. When applied in the “All-on-Four” dental implant concept, AI facilitates immediate prosthetic restorations and meets the demand for expert guidance. This integration boosts the long-term success of surgical outcomes by providing real-time support and improving patient education and postoperative satisfaction. This study aimed to evaluate the effectiveness of three AI-powered chatbots—ChatGPT 4.0, OpenEvidence, and MediSearch—in answering frequently asked questions regarding the All-on-Four dental implant concept. This study investigated the response accuracy of three AI-powered chatbots to common queries about the All-on-Four dental implant concept. Using alsoasked.com, twenty pertinent questions—ten patient-focused and ten technical—were identified. Oral and maxillofacial surgeons evaluated the chatbot responses using a 5-point Likert scale. Statistical analysis was performed with the Kruskal-Wallis test, supplemented by pairwise Mann-Whitney U tests with Bonferroni correction, to assess the significance of differences among the chatbots’ performances. The Kruskal-Wallis test showed statistically significant differences between the three chatbots for both patient and technical questions (p < 0.01). Pairwise comparisons were evaluated using the Mann-Whitney U test. While significant differences were found among each chatbot for patient questions, no significant difference was observed between ChatGPT and MediSearch for technical questions (p = 0.158). When comparing responses of the same chatbot to patient and technical questions, it was found that MediSearch performed better in technical questions (p < 0.001). Advancements in technology have made AI-powered chatbots an inevitable influence in specialized medical fields such as Oral, Maxillofacial Surgery. Our findings indicate that these chatbots can provide valuable information for patients undergoing medical procedures and serve as a resource for healthcare professionals.

This retrospective study evaluated alterations in trabecular bone structure after lateral window and transcrestal sinus floor elevation techniques using fractal analysis of panoramic radiographs, with a focus on comparing ossification patterns. This STROBE compliant retrospective radiographic cohort included 46 sinus lift procedures (transcrestal without graft: n = 21; lateral window with xenograft: n = 25) performed between 2020 and 2024. For each case, two panoramic radiographs were analyzed on the surgery week (T0) and at 6 months (T1) yielding 92 images. Regions of interest (30 × 30 px) were placed apical to the implant site. Images were pre-processed according to the White–Rudolph protocol, and fractal dimension (FD) was calculated in ImageJ using the box-counting method. Normality was confirmed; paired t-tests assessed within-group change and independent t-tests compared groups. Intra-rater reliability was evaluated using the intraclass correlation coefficient. In the transcrestal group, a significant increase in FD values was observed between T0 and T1 (p < 0.001). In contrast, the lateral window approach group showed a statistically significant decrease in FD values over time (p = 0.0032). The FD values in the lateral window approach group were significantly higher than in the transcrestal group at both T0 (p < 0.001) and T1 (p = 0.009). Fractal analysis demonstrated distinct bone remodeling patterns between transcrestal and lateral window sinus lifting techniques. In the transcrestal group, the natural healing process was characterized by more consistent increases in FD values, whereas xenograft-associated remodeling in the lateral window group was accompanied by a decline. These findings underscore the potential of fractal analysis as a non-invasive modality for monitoring bone quality following augmentation. Not applicable.

Dental trauma represents a common emergency condition requiring rapid and accurate guidance to prevent permanent damage. In urgent scenarios where access to dental professionals may be delayed, large language models (LLMs) have the potential to provide patients with timely and relevant information. The aim of this study was to comparatively evaluate the dentist rated performance of five widely used LLMs in answering frequently asked questions related to dental trauma emergencies across three predefined components: accuracy, comprehensiveness, and clinical applicability. Based on the guidelines of the International Association of Dental Traumatology (IADT), the ToothSOS application, and frequently asked patient questions, 27 open-ended questions in Turkish were prepared and divided into five clinical subcategories: avulsion, post-replantation care, luxation, fractures, and other traumas. The questions were posed to the models ChatGPT-4o, Claude 3.5, DeepSeek, Microsoft Copilot, and Gemini 2.0 Flash. Twenty experienced dentists evaluated the responses using a 5-point Likert scale, with the evaluators jointly considering three predefined components: accuracy, comprehensiveness, and clinical applicability. A total of 2,700 individual ratings were analyzed using the Friedman test, Bonferroni-corrected Wilcoxon test, and Intraclass Correlation Coefficient (ICC). A significant difference in overall performance was observed among the models (p < 0.001). ChatGPT-4o achieved the highest mean score (4.63 ± 0.57), whereas Gemini received the lowest score (3.87 ± 0.91). Claude, DeepSeek, and Copilot demonstrated similar, moderate performance, ranging approximately between 4.1 and 4.3. Median values were 5 (IQR 4–5) for ChatGPT-4o and Claude and 4 (IQR 3–5) for the other models, indicating that the responses of ChatGPT-4o and Claude were rated more consistently high. Within each model, no statistically significant differences were observed in mean Likert scores across clinical subcategories (p > 0.05). Although LLMs may not be able to replace professional clinical examination, they may serve as a rapid supportive source of patient-oriented information in dental trauma emergencies where access to a dentist is limited. However, model dependent differences, highlight the need for regular verification before patient facing use. The online version contains supplementary material available at 10.1186/s12903-026-08037-8.

Aim: The aim of this study is to classify accessory mandibular canals (AMC) and investigate their association with the dimensions of the mandibular canal (MC) to enhance surgical planning and prevent complications in dental treatments. Methods: Cone-beam computed tomography (CBCT) images were evaluated. AMC’s frequency, length, and diameter, including dental, superior, inferior, forward-open, forward-closed, and retromolar types, were determined. Additionally, the dimensions of the MC, including its length and diameter, were measured, and the relationship between the AMC and MC was statistically analyzed. Descriptive statistics, chi-square test, independent samples t-test (for normally distributed data), Kruskal-Wallis test (for non-normally distributed data), and Tamhane post hoc test were used for statistical analysis of the data. Results: AMC was identified in 82 of the 222 hemimandibles examined (36.9%). It was found that the length and diameter of AMCs varied significantly depending on the AMC type (p = 0.000). The diameter of the dental type AMCs (mean 0.40 ± 0.22 mm) was considerably smaller than that of other AMC types (mean 0.86 ± 0.37 mm). The length and diameter of the MC were measured as 69.20 ± 5.10 mm and 2.96 ± 0.57 mm, respectively. While MC length was not found to influence the presence of AMC (p = 0.785), MC diameter was significantly associated with the occurrence of AMC (p = 0.000). Conclusions: AMC, which is critical for improving surgical planning and reducing the risk of complications in dental procedures, is not uncommon. Their presence should be carefully evaluated, particularly in cases where the MC has a larger diameter.